BLANKET: Anonymizing Faces in Infant Video Recordings

TL;DR

BLANKET is a novel method for anonymizing infant faces in videos by generating and seamlessly swapping faces to protect identity while maintaining facial attributes and expression consistency.

Contribution

The paper introduces BLANKET, a two-stage approach combining diffusion-based face inpainting and temporally consistent face swapping for infant video anonymization.

Findings

Outperforms DeepPrivacy2 in de-identification and attribute preservation

Maintains facial expressions and pose for downstream tasks

Reduces artifacts compared to existing methods

Abstract

Ensuring the ethical use of video data involving human subjects, particularly infants, requires robust anonymization methods. We propose BLANKET (Baby-face Landmark-preserving ANonymization with Keypoint dEtection consisTency), a novel approach designed to anonymize infant faces in video recordings while preserving essential facial attributes. Our method comprises two stages. First, a new random face, compatible with the original identity, is generated via inpainting using a diffusion model. Second, the new identity is seamlessly incorporated into each video frame through temporally consistent face swapping with authentic expression transfer. The method is evaluated on a dataset of short video recordings of babies and is compared to the popular anonymization method, DeepPrivacy2. Key metrics assessed include the level of de-identification, preservation of facial attributes, impact on human pose estimation (as an example of a downstream task), and presence of artifacts. Both methods alter the identity, and our method outperforms DeepPrivacy2 in all other respects. The code is available as an easy-to-use anonymization demo at https://github.com/ctu-vras/blanket-infant-face-anonym.